© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127633
    Prev
    Next
    INDEX
    Explanations

    receiving confirmation, baptism, threats, oxygen, mail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    筇
    -1.84
     моей
    -1.81
    ſam
    -1.79
    嚶
    -1.79
    ar
    -1.77
    тием
    -1.73
     atractivos
    -1.71
     нашего
    -1.71
    阏
    -1.71
     THESE
    -1.70
    POSITIVE LOGITS
     from
    1.83
    Although
    1.77
    Though
    1.60
     Though
    1.58
    There
    1.57
     Although
    1.56
    Despite
    1.55
    مقدمه
    1.53
     any
    1.52
    While
    1.51
    Activations Density 0.014%

    No Known Activations